---
title: Sentiment Analysis
emoji: 🐨
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
short_description: Sentiment analysis MCP server using Gradio.
---

# Sentiment Analysis MCP

A Python-based sentiment analysis application using TextBlob and Gradio that provides real-time sentiment analysis through a web interface.

## Features

- **Real-time sentiment analysis** using TextBlob's natural language processing
- **Interactive web interface** powered by Gradio
- **Comprehensive metrics** including polarity, subjectivity, and sentiment assessment
- **MCP server integration** for enhanced functionality
- **Easy-to-use interface** with instant results

## What It Analyzes

- **Polarity**: Sentiment score from -1.0 (very negative) to +1.0 (very positive)
- **Subjectivity**: Objectivity score from 0.0 (objective) to 1.0 (subjective)
- **Assessment**: Simple classification as "positive", "negative", or "neutral"

## Installation

### Prerequisites

- Python 3.7 or higher
- pip package manager

### Setup

1. **Clone the repository**:
   ```bash
   git clone https://github.com/GitBuntu/sentiment-analysis-mcp.git
   cd sentiment-analysis-mcp
   ```

2. **Create a virtual environment** (recommended):
   ```bash
   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   ```

3. **Install dependencies**:
   ```bash
   pip install -r requirements.txt
   ```

## Usage

### Running the Application

1. **Start the application**:
   ```bash
   python app.py
   ```

2. **Open your web browser** and navigate to the local URL displayed in the terminal (typically `http://127.0.0.1:7860`)

3. **Enter text** in the input box and get instant sentiment analysis results

### Example Results

**Input**: "The food was delicious but the service was slow and disappointing."

**Output**:
```json
{
  "polarity": 0.1,
  "subjectivity": 0.9,
  "assessment": "positive"
}
```

## MCP Server Configuration

### SSE Support

Some MCP clients don't support SSE-based MCP Servers. In those cases, use mcp-remote:

```json
{
  "mcpServers": {
    "gradio": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:7860/gradio_api/mcp/sse"
      ]
    }
  }
}
```

### Connection Issues

If you encounter connection problems:
- Try restarting both the client and server
- Check that the server is running and accessible
- Verify that the MCP schema is available at the expected URL

## Testing

The project includes a comprehensive test file (`test_texts.txt`) with examples for:

- **Positive sentiment** - Happy, excited, satisfied expressions
- **Negative sentiment** - Angry, disappointed, frustrated expressions  
- **Neutral sentiment** - Factual, objective statements
- **Mixed sentiment** - Texts with both positive and negative elements
- **Highly subjective** - Personal opinions and emotional expressions
- **Objective statements** - Factual information with minimal emotion
- **Edge cases** - Empty strings, punctuation, negations, ambiguous text

### Sample Test Cases

| Text | Expected Polarity | Expected Assessment |
|------|------------------|-------------------|
| "I absolutely love this new restaurant!" | High positive (~0.8) | positive |
| "This product is terrible." | High negative (~-0.8) | negative |
| "The meeting is at 3 PM." | Near zero (~0.0) | neutral |
| "The food was delicious but service was slow." | Slightly positive | positive |

## Project Structure

```
sentiment-analysis-mcp/
├── app.py              # Main application file
├── requirements.txt    # Python dependencies
├── test_texts.txt     # Test cases for sentiment analysis
├── README.md          # Project documentation
└── venv/              # Virtual environment (created after setup)
```

## Dependencies

- **textblob>=0.17.1** - Natural language processing library for sentiment analysis
- **gradio>=4.0.0** - Web interface framework for machine learning applications

## How It Works

1. **Text Processing**: Input text is processed using TextBlob's natural language processing capabilities
2. **Sentiment Calculation**: TextBlob calculates polarity and subjectivity scores
3. **Classification**: The application categorizes sentiment as positive, negative, or neutral based on polarity
4. **Web Interface**: Gradio provides an interactive web interface for easy testing and usage

## Use Cases

- **Social media monitoring** - Analyze customer feedback and comments
- **Product reviews** - Understand customer satisfaction from reviews
- **Survey analysis** - Process open-ended survey responses
- **Content moderation** - Identify potentially negative content
- **Market research** - Analyze public opinion on topics or products

## Contributing

1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add some amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request

## License

This project is open source and available under the [MIT License](LICENSE).

## Limitations

- **Language Support**: Currently optimized for English text
- **Context Understanding**: May not fully understand complex sarcasm or context-dependent sentiment
- **Domain Specificity**: General-purpose model may not be optimized for specific domains
- **Sentence Length**: Very short texts may not provide reliable sentiment scores

## Future Enhancements

- [ ] Support for multiple languages
- [ ] Custom model training capabilities
- [ ] Batch processing for multiple texts
- [ ] Export results to CSV/JSON
- [ ] REST API endpoints
- [ ] Docker containerization
- [ ] Advanced visualization charts

## Support

If you encounter any issues or have questions:

1. Check the [test_texts.txt](test_texts.txt) file for examples
2. Review the error messages in the terminal
3. Open an issue on GitHub with detailed information about the problem

## Acknowledgments

- **TextBlob** - For providing excellent natural language processing capabilities
- **Gradio** - For the easy-to-use web interface framework
- **Python Community** - For the amazing ecosystem of tools and libraries